Raw Inference API

Unfiltered llms: The API for Uncensored Generative AI

Build uncensored applications with our 100,000-token context window API that never refuses lawful adult content or creative writing.

100,000 token context window
Zero monthly subscription fees
Crypto only top-ups

Try with trial credit View documentation

Test with one call

curl https://api.unfilteredllms.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Return current server time in ISO format"}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.unfilteredllms.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.unfilteredllms.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

$0.15
per 1M input tokens: $0.50
Output tokens / 1M: 100,000
token context: $0.50
trial credit: 300
requests per minute

Core features

OpenAI-Compatible Endpoints

Drop-in replacement using standard chat-completions endpoints for rapid integration.

Streaming Support

Receive real-time tokens via Server-Sent Events with usage data in the final chunk.

JSON Mode

Enforce structured output strictly with response_format json_object for reliable parsing.

Function Calling

Execute tools and pass tool_choice parameters for dynamic agent workflows.

No Data Training

We do not use your prompts for training, preserving your creative privacy.

Persistent Credits

Prepaid tokens never expire, so you only pay for the inference you use.

Setup process

Create Account

Add Crypto Credit

Top up with USDT or USDC to start sending requests immediately.

Send First Request

Point your client to our base URL and receive text output.

Community projects

Unfiltered AI Chat

Power conversational agents that answer controversial questions without standard guardrails.

Adult Content Generation

Serve creative writing and roleplay scenarios without unexpected content refusals.

Long-Context Coding

Process entire codebases within the 100,000-token window for accurate analysis.

Research Inference

Retrieve unaligned model outputs for security research or raw data tasks.

unfiltered LLMs for Adult Content, Coding, and Roleplay

unfiltered LLMs provide raw inference without corporate guardrails, letting you build NSFW apps or complex roleplay bots with zero refusals for lawful content.

Uncensored AI Roleplay

Deliver immersive, unrestricted narratives without sudden topic shifts or safety blocks interrupting the experience.

Code Generation

Receive direct, unfiltered technical outputs without unnecessary conversational filler or conservative constraints.

Adult Content

Generate mature material freely, knowing only the hard limit on minors applies.

Real Cost Examples: How Many Tokens Your $50 Buys

Your $50 credit buys raw inference without subscription locks. At $0.15 per 1M input tokens and $0.50 per 1M output tokens, costs scale directly with usage. For example, a 10,000-token prompt generating 2,000 tokens costs roughly $0.0025. This allows thousands of requests before your balance drops. Errors incur zero charges. Credit never expires, so you retain value indefinitely while paying only for what you actually process.

Built for Creators; Not for Enterprise SLAs

Our API serves developers who need raw inference, not corporate guarantees. You get 100,000 tokens of context and streaming via SSE. We do not offer SLA percentages, SOC2 certifications, or on-prem deployment. If you require HIPAA compliance or dedicated model routing, look elsewhere. This is a straightforward pay-as-you-go tool for unrestricted generation.

5 Signs You Are Using a Filtered Provider Instead of Raw Inference

Filtered providers block lawful content; our uncensored LLMs API serves raw inference without corporate guardrails. Identify if you are paying for censorship rather than compute.

Sign	Filtered Provider	Raw Inference (Ours)
Content Blocking	Refuses adult or niche topics	Answers without refusals
Pricing Model	Monthly subscription fee	$0.15/1M input tokens
Training Usage	Uses prompts for training	Never trains on your data	Context Window	Short limits (e.g., 4K tokens)	100,000 tokens
Refund Policy	Strict credit expiration	Credit never expires
Signup	Requires phone verification	Email or Google only

Visit the dashboard and click "Get API key." You can sign in with Google or create a password-based account using just your email address. No phone verification is required.
Your unique API key appears immediately on screen. Copy this string securely, as it authenticates every request you send to our endpoints.
Point your OpenAI-compatible SDK to our base URL. Send a simple prompt, and receive raw, uncensored text output instantly.

The Uncensored API Selection Checklist

Verify the model ID explicitly, not just marketing copy. Our provider uses uncensored as the identifier. Check the context window: we support 100,000 tokens. Confirm pricing structure. We charge $0.15 per 1M input tokens. Ensure no subscription fees apply. Verify payment methods. We accept only crypto. Check privacy terms. We do not train on your prompts. Test streaming support. We offer Server-Sent Events for real-time output.

Common questions

What are unfiltered LLMs capabilities compared to standard models?

They remove content refusals for lawful adult topics. Our endpoint serves a single uncensored model via standard OpenAI-compatible routes. You get streaming, function calling, and JSON mode without extra filters blocking your output.

Which payment methods do you accept?

Crypto only: USDT on TRC20 or USDC on Base, any whole amount from $20 to $500. Bonus credit applies from $50.

Is this a standard OpenAI-compatible interface?

Yes. We use the standard /v1/chat/completions endpoint structure. You can use the official OpenAI SDKs by simply updating the base_url and providing your API key. It works with any compatible client.

How much does it cost to run the model?

It costs $0.15 per million input tokens and $0.50 per million output tokens. Errors and refusals incur no charge. You pay only for real usage with prepaid credit that never expires.

Can I use cryptocurrency to top up my balance?

Yes. We accept USDT on TRC20 or USDC on Base. Top-ups range from $20 to $500. You receive bonus credit for higher amounts.

What is the context window limit for requests?

The model supports a 100,000 token context window. You can generate up to 16,000 output tokens per request. Streaming is available via SSE, and you can control temperature, top_p, and other parameters.

Get your API key now

Try with trial credit